How to Use the Junta de Andalucía (Portal) MCP in OpenAI Agents SDK

Q: Can OpenAI Agents SDK handle large tables from the Junta de Andalucía (Portal) without crashing?

Yes. Use searchdatastore to filter rows and columns on the portal side instead of downloading entire datasets. This keeps the payload small and prevents your OpenAI Agents SDK context window from overflowing.

Q: What happens if a dataset format changes on the portal?

Your agent should call getresource to check the format field before parsing. If the format changes from CSV to JSON, the agent detects the shift in the metadata and adapts its parsing logic.

Feed real-time Andalusian public datasets directly to your OpenAI Agents SDK pipelines with zero manual configuration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Junta de Andalucía (Portal) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Junta de Andalucía (Portal) to OpenAI Agents SDK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Junta de Andalucía (Portal) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map public datasets using OpenAI Agents SDK

`list_packages` pulls the exact names of active public datasets directly from the Andalusian portal into your agent's context. Your agent uses this tool first to find where the regional government publishes its economic, environmental, or municipal records. Once it has the names, the agent calls `get_package` to inspect the metadata. This lets your OpenAI Agents SDK pipeline verify the schema and update frequency before attempting to download raw files.

Query raw tables with this MCP Server

`search_datastore` acts as the direct query engine for tabular data hosted on the Andalusian portal. This tool lets your OpenAI Agents SDK agent run SQL-like searches against specific resource tables without downloading gigabytes of CSVs. The agent pairs this with `get_resource` to extract the correct file identifiers. It keeps your operational footprint low because you only pull the exact rows required for your analytical tasks.

Navigate regional organizations programmatically

`list_organizations` exposes the entire hierarchy of Andalusian government agencies publishing data on the portal. Your OpenAI Agents SDK system uses this to filter data sources by specific departments like agriculture or finance. By combining this with `list_groups`, your agent groups datasets into thematic buckets. It builds a structured index of regional resources without hardcoding any MCP Server paths.

Setup guide

Set up Junta de Andalucía (Portal) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Junta de Andalucía (Portal) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Junta de Andalucía (Portal) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Junta de Andalucía (Portal) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Junta de Andalucía (Portal) Agent",
            instructions="You have access to Junta de Andalucía (Portal) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Junta de Andalucía. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Junta de Andalucía (Portal) now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Junta de Andalucía (Portal) MCP in OpenAI Agents SDK

Install the SDK, initialize MCPServerStreamableHttp pointing to the Vinkius endpoint, and register it in your Agent constructor. The agent automatically discovers the tools like `list_packages` and `search_datastore` on startup.

Yes. Use `search_datastore` to filter rows and columns on the portal side instead of downloading entire datasets. This keeps the payload small and prevents your OpenAI Agents SDK context window from overflowing.

Yes, the server processes concurrent requests for metadata and resource extraction. Your OpenAI Agents SDK system can trigger `get_package` and `get_resource` simultaneously to speed up data gathering.

Your agent should call `get_resource` to check the format field before parsing. If the format changes from CSV to JSON, the agent detects the shift in the metadata and adapts its parsing logic.

All queries sent to the Vinkius MCP sandbox are ephemeral and run in isolated V8 environments. No search terms used in `search_datastore` are stored or logged after the request completes.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript